Bytedance Inc.

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

An open-source SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skills and subagents, it handles different levels of tasks that could take minutes to hours.

Pioneering Automated GUI Interaction with Native Agents

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

ComfyUI Lumi Batcher is a batch processing extension plugin designed for ComfyUI, aiming to improve workflow debugging efficiency. Traditional debugging methods require adjusting parameters one by one, while this tool significantly enhances work efficiency through batch processing capabilities.

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Taming Stable Diffusion for Lip Sync!

:fire: ByteHook is an Android PLT hook library which supports armeabi-v7a, arm64-v8a, x86 and x86_64.

DreamID-V: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

PatchEval: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities

An acceleration library that supports arbitrary bit-width combinatorial quantization operations

KV cache store for distributed LLM inference

Official repository for our paper "FullStack Bench: Evaluating LLMs as Full Stack Coders"

Web-Bench is a benchmark designed to evaluate the performance of LLMs in actual Web development.

Valley is a cutting-edge multimodal large model designed to handle a variety of tasks involving text, images, and video data.

🍎Transform an SVG icon into multiple themes, and generate React icons，Vue icons，svg icons

A blazingly fast JSON serializing & deserializing library

Running BERT without Padding

[NeurIPS 2023] This repo contains the code for our paper Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

FlowGram is an extensible workflow development framework with built-in canvas, form, variable, and materials that helps developers build AI workflow platforms faster and simpler.

PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant references, to ultimately obtain comprehensive and accurate results for complex scholarly queries.

A simple and easy-to-use Go mocking library derived from ByteDance's internal best practices

Tarsier -- a family of large-scale video-language models, which is designed to generate high-quality video descriptions , together with good capability of general video understanding.

A Lightweight Recommendation System

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052